Legal claims defining the scope of protection. Each claim is shown in both the original legal language and a plain English translation.
1. A master system for adjusting oversubscription loading, comprising: an interface configured to: receive a set of performance data from a set of worker systems; and a processor configured to: determine a feedback indication for a worker system of the set of worker systems based at least in part on the set of performance data, wherein the feedback indication is used to adjust eviction criteria of an oversubscription controller on the worker system, and wherein the determining of the feedback indication comprises operations to: perform the following: A) determine a response time for an application performing requests sent to the application to obtain a stability indicator; and in response to a determination that the response time is greater than or equal to a maximum response time threshold, include the stability indicator in the feedback indication; B) compare first tasks under ideal conditions over a first period of time with no potentially interfering workloads present on a worker with second tasks over a second period of time with one or more other interfering workloads present on the same worker to obtain a software experiment data; and in response to a determination that a decrease in the second tasks over the second period of time, based on a comparison of the first tasks and the second tasks, is greater than or equal to a maximum decrease threshold, include the software experiment data in the feedback indication; C) determine whether two or more tasks that are scheduled on the same worker use a shared resource to obtain a task interference; and in response to a determination that the two or more tasks that are scheduled on the same worker use the shared resource, include the task interference in the feedback indication; and D) include a classification of performance data in the feedback indication, the classification of performance data including a processor intensive classification being a dominant usage of system resources, a memory intensive classification being a dominant usage of system resources, a network access intensive classification being a dominant usage of system resources, a disk access intensive classification being a dominant usage of system resources, or any combination thereof; and adjust the oversubscription controller of the worker system to evict a job, based on the provided feedback indication, useable by the worker system.
A master system adjusts oversubscription loading. An interface receives performance data from worker systems. A processor determines a feedback indication for each worker, used to adjust its oversubscription controller's eviction criteria. This feedback is determined by: A) finding a "stability indicator" when an application's response time exceeds a maximum threshold; B) generating "software experiment data" by comparing tasks under ideal vs. interfering workloads and detecting significant performance drops; C) identifying "task interference" if co-scheduled tasks on a worker use shared resources; and D) including a classification of performance data by dominant resource usage (processor, memory, network, disk intensive). The system then adjusts the worker's oversubscription controller to evict a job based on this feedback.
2. The system of claim 1 , wherein the feedback indication is used to adjust a set point on the oversubscription controller.
A master system adjusts oversubscription loading. An interface receives performance data from worker systems. A processor determines a feedback indication for each worker, which is used to adjust a *set point* on its oversubscription controller's eviction criteria. This feedback is determined by: A) finding a "stability indicator" when an application's response time exceeds a maximum threshold; B) generating "software experiment data" by comparing tasks under ideal vs. interfering workloads and detecting significant performance drops; C) identifying "task interference" if co-scheduled tasks on a worker use shared resources; and D) including a classification of performance data by dominant resource usage (processor, memory, network, disk intensive). The system then adjusts the worker's oversubscription controller to evict a job based on this feedback, using the adjusted set point.
3. The system of claim 2 , wherein the set point comprises a desired processor load set point.
A master system adjusts oversubscription loading. An interface receives performance data from worker systems. A processor determines a feedback indication for each worker, which is used to adjust a *desired processor load set point* on its oversubscription controller's eviction criteria. This feedback is determined by: A) finding a "stability indicator" when an application's response time exceeds a maximum threshold; B) generating "software experiment data" by comparing tasks under ideal vs. interfering workloads and detecting significant performance drops; C) identifying "task interference" if co-scheduled tasks on a worker use shared resources; and D) including a classification of performance data by dominant resource usage (processor, memory, network, disk intensive). The system then adjusts the worker's oversubscription controller to evict a job based on this feedback, using the adjusted processor load set point.
4. The system of claim 2 , wherein the set point comprises a desired memory usage set point.
A master system adjusts oversubscription loading. An interface receives performance data from worker systems. A processor determines a feedback indication for each worker, which is used to adjust a *desired memory usage set point* on its oversubscription controller's eviction criteria. This feedback is determined by: A) finding a "stability indicator" when an application's response time exceeds a maximum threshold; B) generating "software experiment data" by comparing tasks under ideal vs. interfering workloads and detecting significant performance drops; C) identifying "task interference" if co-scheduled tasks on a worker use shared resources; and D) including a classification of performance data by dominant resource usage (processor, memory, network, disk intensive). The system then adjusts the worker's oversubscription controller to evict a job based on this feedback, using the adjusted memory usage set point.
5. The system of claim 2 , wherein the set point comprises a desired network usage set point.
A master system adjusts oversubscription loading. An interface receives performance data from worker systems. A processor determines a feedback indication for each worker, which is used to adjust a *desired network usage set point* on its oversubscription controller's eviction criteria. This feedback is determined by: A) finding a "stability indicator" when an application's response time exceeds a maximum threshold; B) generating "software experiment data" by comparing tasks under ideal vs. interfering workloads and detecting significant performance drops; C) identifying "task interference" if co-scheduled tasks on a worker use shared resources; and D) including a classification of performance data by dominant resource usage (processor, memory, network, disk intensive). The system then adjusts the worker's oversubscription controller to evict a job based on this feedback, using the adjusted network usage set point.
6. The system of claim 1 , wherein the eviction criteria comprises newest first.
A master system adjusts oversubscription loading. An interface receives performance data from worker systems. A processor determines a feedback indication for each worker, used to adjust its oversubscription controller's eviction criteria, specifically implementing a *newest first* eviction policy. This feedback is determined by: A) finding a "stability indicator" when an application's response time exceeds a maximum threshold; B) generating "software experiment data" by comparing tasks under ideal vs. interfering workloads and detecting significant performance drops; C) identifying "task interference" if co-scheduled tasks on a worker use shared resources; and D) including a classification of performance data by dominant resource usage (processor, memory, network, disk intensive). The system then adjusts the worker's oversubscription controller to evict a job based on this feedback, prioritizing newer jobs for eviction.
7. The system of claim 1 , wherein the eviction criteria comprises most processor use first.
A master system adjusts oversubscription loading. An interface receives performance data from worker systems. A processor determines a feedback indication for each worker, used to adjust its oversubscription controller's eviction criteria, specifically implementing a *most processor use first* eviction policy. This feedback is determined by: A) finding a "stability indicator" when an application's response time exceeds a maximum threshold; B) generating "software experiment data" by comparing tasks under ideal vs. interfering workloads and detecting significant performance drops; C) identifying "task interference" if co-scheduled tasks on a worker use shared resources; and D) including a classification of performance data by dominant resource usage (processor, memory, network, disk intensive). The system then adjusts the worker's oversubscription controller to evict a job based on this feedback, prioritizing jobs consuming the most processor resources for eviction.
8. The system of claim 1 , wherein the eviction criteria comprises most memory use first.
A master system adjusts oversubscription loading. An interface receives performance data from worker systems. A processor determines a feedback indication for each worker, used to adjust its oversubscription controller's eviction criteria, specifically implementing a *most memory use first* eviction policy. This feedback is determined by: A) finding a "stability indicator" when an application's response time exceeds a maximum threshold; B) generating "software experiment data" by comparing tasks under ideal vs. interfering workloads and detecting significant performance drops; C) identifying "task interference" if co-scheduled tasks on a worker use shared resources; and D) including a classification of performance data by dominant resource usage (processor, memory, network, disk intensive). The system then adjusts the worker's oversubscription controller to evict a job based on this feedback, prioritizing jobs consuming the most memory resources for eviction.
9. The system of claim 1 , wherein the eviction criteria comprises most network use first.
A master system adjusts oversubscription loading. An interface receives performance data from worker systems. A processor determines a feedback indication for each worker, used to adjust its oversubscription controller's eviction criteria, specifically implementing a *most network use first* eviction policy. This feedback is determined by: A) finding a "stability indicator" when an application's response time exceeds a maximum threshold; B) generating "software experiment data" by comparing tasks under ideal vs. interfering workloads and detecting significant performance drops; C) identifying "task interference" if co-scheduled tasks on a worker use shared resources; and D) including a classification of performance data by dominant resource usage (processor, memory, network, disk intensive). The system then adjusts the worker's oversubscription controller to evict a job based on this feedback, prioritizing jobs with the most network use for eviction.
10. The system of claim 1 , wherein the processor is further configured to assign the high-priority job to the worker system.
A master system adjusts oversubscription loading. An interface receives performance data from worker systems. A processor determines a feedback indication for each worker, and *also assigns high-priority jobs to worker systems*. This indication is used to adjust the worker's oversubscription controller's eviction criteria. The feedback is determined by: A) finding a "stability indicator" when an application's response time exceeds a maximum threshold; B) generating "software experiment data" by comparing tasks under ideal vs. interfering workloads and detecting significant performance drops; C) identifying "task interference" if co-scheduled tasks on a worker use shared resources; and D) including a classification of performance data by dominant resource usage (processor, memory, network, disk intensive). The system then adjusts the worker's oversubscription controller to evict a job based on this feedback.
11. The system of claim 1 , wherein the processor is further configured to determine whether an assignment of the high-priority job to the worker system exceeds a subscription threshold based at least in part on the set of performance data.
A master system adjusts oversubscription loading. An interface receives performance data from worker systems. A processor determines a feedback indication for each worker, and *further determines if assigning a high-priority job to a worker system would exceed a subscription threshold*, based on the collected performance data. This feedback indication is used to adjust the worker's oversubscription controller's eviction criteria. The feedback is determined by: A) finding a "stability indicator" when an application's response time exceeds a maximum threshold; B) generating "software experiment data" by comparing tasks under ideal vs. interfering workloads and detecting significant performance drops; C) identifying "task interference" if co-scheduled tasks on a worker use shared resources; and D) including a classification of performance data by dominant resource usage (processor, memory, network, disk intensive). The system then adjusts the worker's oversubscription controller to evict a job based on this feedback.
12. A method for adjusting oversubscription loading, comprising: receiving a set of performance data from a set of worker systems; determining, using a processor at a master system, a feedback indication for a worker system of the set of worker systems based at least in part on the set of performance data, wherein the feedback indication is used to adjust eviction criteria of an oversubscription controller on the worker system, and wherein the determining of the feedback indication comprises: performing the following: A) determining a response time for an application performing requests sent to the application to obtain a stability indicator; and in response to a determination that the response time is greater than or equal to a maximum response time threshold, including the stability indicator in the feedback indication; B) comparing first tasks under ideal conditions over a first period of time with no potentially interfering workloads present on a worker with second tasks over a second period of time with one or more other interfering workloads present on the same worker to obtain a software experiment data; and in response to a determination that a decrease in the second tasks over the second period of time, based on a comparison of the first tasks and the second tasks, is greater than or equal to a maximum decrease threshold, including the software experiment data in the feedback indication; C) determining whether two or more tasks that are scheduled on the same worker use a shared resource to obtain a task interference; and in response to a determination that the two or more tasks that are scheduled on the same worker use the shared resource, including the task interference in the feedback indication; and D) including a classification of performance data in the feedback indication, the classification of performance data including a processor intensive classification being a dominant usage of system resources, a memory intensive classification being a dominant usage of system resources, a network access intensive classification being a dominant usage of system resources, a disk access intensive classification being a dominant usage of system resources, or any combination thereof; and adjusting the oversubscription controller of the worker system to evict a job, based on the provided feedback indication, useable by the worker system.
A method adjusts oversubscription loading. It involves receiving performance data from worker systems. A master system's processor determines a feedback indication for each worker, which adjusts the worker's oversubscription controller's eviction criteria. This determination includes: A) finding a "stability indicator" if an application's response time exceeds a maximum threshold; B) generating "software experiment data" by comparing tasks under ideal vs. interfering workloads and detecting significant performance drops; C) identifying "task interference" if co-scheduled tasks on a worker use shared resources; and D) including a classification of performance data by dominant resource usage (processor, memory, network, disk intensive). The method then adjusts the worker's oversubscription controller to evict a job based on this feedback.
13. A computer program product for oversubscription loading, the computer program product being embodied in a non-transitory computer readable storage medium and comprising computer instructions for: receiving a set of performance data from a set of worker systems; determining, using a processor at a master system, a feedback indication for a worker system of the set of worker systems based at least in part on the set of performance data, wherein the feedback indication is used to adjust eviction criteria of an oversubscription controller on the worker system, and wherein the determining of the feedback indication comprises: performing the following: A) determining a response time for an application performing requests sent to the application to obtain a stability indicator; and in response to a determination that the response time is greater than or equal to a maximum response time threshold, including the stability indicator in the feedback indication; B) comparing first tasks under ideal conditions over a first period of time with no potentially interfering workloads present on a worker with second tasks over a second period of time with one or more other interfering workloads present on the same worker to obtain a software experiment data; and in response to a determination that a decrease in the second tasks over the second period of time, based on a comparison of the first tasks and the second tasks, is greater than or equal to a maximum decrease threshold, including the software experiment data in the feedback indication; C) determining whether two or more tasks that are scheduled on the same worker use a shared resource to obtain a task interference; and in response to a determination that the two or more tasks that are scheduled on the same worker use the shared resource, including the task interference in the feedback indication; and D) including a classification of performance data in the feedback indication, the classification of performance data including a processor intensive classification being a dominant usage of system resources, a memory intensive classification being a dominant usage of system resources, a network access intensive classification being a dominant usage of system resources, a disk access intensive classification being a dominant usage of system resources, or any combination thereof; and adjusting the oversubscription controller of the worker system to evict a job, based on the provided feedback indication, useable by the worker system.
A non-transitory computer readable storage medium stores instructions for adjusting oversubscription loading. These instructions, when executed by a master system's processor, cause it to: receive performance data from worker systems; and determine a feedback indication for each worker. This feedback adjusts the worker's oversubscription controller's eviction criteria and is determined by: A) finding a "stability indicator" if an application's response time exceeds a maximum threshold; B) generating "software experiment data" by comparing tasks under ideal vs. interfering workloads and detecting significant performance drops; C) identifying "task interference" if co-scheduled tasks on a worker use shared resources; and D) including a classification of performance data by dominant resource usage (processor, memory, network, disk intensive). Finally, the instructions cause the system to adjust the worker's oversubscription controller to evict a job based on this feedback.
Unknown
August 4, 2020
Browse 5M+ US patents with plain-English claim translations and AI-generated analysis.